HoloMotion-1 Technical Report
This report presents HoloMotion-1, a humanoid motion foundation model for zero-shot whole-body motion tracking. It scales control-policy training with a large-scale hybrid motion corpus that combines video-reconstructed motions for diversity with high-fidelity motion capture and in-house data for supervision. The model addresses challenges like reconstruction noise and domain mismatch through a sparse Mixture-of-Experts Transformer with KV-cache for real-time control and sequence-level training. Experiments show robust generalization, improved tracking accuracy, and direct transfer to a real humanoid robot without fine-tuning.
[2605.15336] HoloMotion-1 Technical Report
[Submitted on 14 May 2026]
Title:HoloMotion-1 Technical Report
View a PDF of the paper titled HoloMotion-1 Technical Report, by Maiyue Chen and 9 other authors
View PDF HTML (experimental)
Abstract:In this report, we present HoloMotion-1, a humanoid motion foundation model for zero-shot whole-body motion tracking. A key innovation of HoloMotion-1 is to scale control-policy training with a large-scale hybrid motion corpus, where video-reconstructed motions from in-the-wild videos provide the dominant source of motion diversity, while curated motion-capture and in-house motion data provide higher-fidelity supervision and deployment-oriented coverage. This data regime enables HoloMotion-1 to move beyond conventional MoCap-only training and exposes the policy to substantially broader behaviors, capture conditions, and motion styles.
Learning from such heterogeneous data introduces new challenges, including reconstruction noise, source-domain mismatch, uneven motion quality, and the need for temporal modeling under large behavioral variation. To address these challenges, HoloMotion-1 integrates large-capacity temporal modeling, a sparsely activated Mixture-of-Experts Transformer with KV-cache inference for real-time control, and a sequence-level training strategy that improves learning efficiency on extended motion sequences. Extensive experiments on multiple unseen motion benchmarks show that HoloMotion-1 generalizes robustly across diverse motion types and capture conditions, significantly improves tracking accuracy over prior methods, and transfers directly to a real humanoid robot without task-specific fine-tuning.
Comments: 20 pages, 4 figures, 6 tables. Technical report
Subjects:
Robotics (cs.RO); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.15336 [cs.RO]
(or arXiv:2605.15336v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2605.15336
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yucheng Wang [view email] [v1] Thu, 14 May 2026 18:59:43 UTC (1,668 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled HoloMotion-1 Technical Report, by Maiyue Chen and 9 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-05
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)